Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    dates and associated timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukes
    -0.63
     crown
    -0.58
    xxxx
    -0.56
     playthrough
    -0.55
    cour
    -0.54
     overw
    -0.54
    secut
    -0.53
     unlaw
    -0.53
     Sims
    -0.52
     Bung
    -0.51
    POSITIVE LOGITS
     partName
    0.64
    ccording
    0.63
    ategor
    0.62
    Dear
    0.61
    Morning
    0.59
    VIDEO
    0.58
    )--
    0.58
    yrics
    0.58
    reetings
    0.57
     Javier
    0.57
    Act Density 0.088%

    No Known Activations